中文
相关论文

相关论文: Continuous Symmetry Discovery and Enforcement Usin…

200 篇论文

Symmetry detection can improve various machine learning tasks. In the context of continuous symmetry detection, current state of the art experiments are limited to detecting affine transformations. Under the manifold assumption, we outline…

机器学习 · 计算机科学 2024-11-08 Ben Shaw , Abram Magner , Kevin R. Moon

Exploiting symmetry inherent in data can significantly improve the sample efficiency of a learning procedure and the generalization of learned models. When data clearly reveals underlying symmetry, leveraging this symmetry can naturally…

机器学习 · 计算机科学 2024-12-20 Gyeonghoon Ko , Hyunsu Kim , Juho Lee

Symmetry in differential equations reveals invariances and offers a powerful means to reduce model complexity. Lie group analysis characterizes these symmetries through infinitesimal generators, which provide a local, linear criterion for…

数值分析 · 数学 2025-11-14 Max Kreider , John Harlim , Daning Huang

We introduce a machine-learning approach (denoted Symmetry Seeker Neural Network) capable of automatically discovering discrete symmetry groups in physical systems. This method identifies the finite set of parameter transformations that…

Symmetry is widely applied in problems such as the design of equivariant networks and the discovery of governing equations, but in complex scenarios, it is not known in advance. Most previous symmetry discovery methods are limited to linear…

机器学习 · 计算机科学 2025-10-03 Lexiang Hu , Yikang Li , Zhouchen Lin

Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge. While recent advancements have been made…

Symmetry is present throughout nature and continues to play an increasingly central role in physics and machine learning. Fundamental symmetries, such as Poincar\'{e} invariance, allow physical laws discovered in laboratories on Earth to be…

机器学习 · 计算机科学 2025-06-13 Samuel E. Otto , Nicholas Zolman , J. Nathan Kutz , Steven L. Brunton

Recent work has applied supervised deep learning to derive continuous symmetry transformations that preserve the data labels and to obtain the corresponding algebras of symmetry generators. This letter introduces two improved algorithms…

高能物理 - 理论 · 物理学 2023-07-12 Roy T. Forestano , Konstantin T. Matchev , Katia Matcheva , Alexander Roman , Eyup B. Unlu , Sarunas Verner

Symmetry groups allow to transform solutions of differential equations continuously into other solutions. This property can be used for the observability analysis of infinite-dimensional systems with input and output. In this contribution,…

最优化与控制 · 数学 2019-05-28 Bernd Kolar , Markus Schöberl

Symmetry is fundamental to understanding physical systems and can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data, yet discovering these symmetries…

What are the symmetries of a dataset? Whereas the symmetries of an individual data element can be characterized by its invariance under various transformations, the symmetries of an ensemble of data elements are ambiguous due to Jacobian…

高能物理 - 唯象学 · 物理学 2022-09-05 Krish Desai , Benjamin Nachman , Jesse Thaler

Discovering governing equations, whether manually or by data-driven methods, has been central in physics and related areas. Since governing equations are typically constrained by a set of symmetries, using symmetry constraints to restrict…

统计力学 · 物理学 2026-04-03 Junya Yokokura , Kazumasa A. Takeuchi

We consider the problem of learning a function respecting a symmetry from among a class of symmetries. We develop a unified framework that enables symmetry discovery across a broad range of subgroups including locally symmetric, dihedral…

机器学习 · 计算机科学 2023-10-30 Pavan Karjol , Rohan Kashyap , Aditya Gopalan , Prathosh A. P

We propose a data-driven Machine-Learning Symmetry Discovery (MLSD) framework for identifying continuous symmetry generators and their Lie-algebraic structure directly from phase-space trajectory data expressed in canonical coordinates.…

无序系统与神经网络 · 物理学 2026-01-21 Wanda Hou , Molan Li , Yi-Zhuang You

The aim of this paper is to study symmetries of linearly singular differential equations, namely, equations that can not be written in normal form because the derivatives are multiplied by a singular linear operator. The concept of…

数学物理 · 物理学 2009-11-07 Xavier Gracia , Josep M. Pons

Symmetry groups of PDEs allow to transform solutions continuously into other solutions. In this paper, we use this property for the observability analysis of nonlinear PDEs with input and output. Based on a differential-geometric…

最优化与控制 · 数学 2018-07-19 Bernd Kolar , Hubert Rams , Markus Schöberl

In this work, we introduce the Equivariance Seeker Model (ESM), a data-driven method for discovering the underlying finite equivariant symmetry group of an arbitrary function. ESM achieves this by optimizing a loss function that balances…

计算物理 · 物理学 2025-03-06 Pablo Calvo-Barlés , Sergio G. Rodrigo , Luis Martín-Moreno

In this paper, we introduce a natural classification of bar and joint frameworks that possess symmetry. This classification establishes the mathematical foundation for extending a variety of results in rigidity, as well as infinitesimal or…

度量几何 · 数学 2008-08-14 Bernd Schulze

Symmetry is a fundamental concept that has been extensively studied, yet detecting it in complex scenes remains a significant challenge in computer vision. Recent heatmap-based approaches can localize potential regions of symmetry axes but…

计算机视觉与模式识别 · 计算机科学 2025-10-16 Wongyun Yu , Ahyun Seo , Minsu Cho

The starting point of this work is a framework allowing to model systems with dynamic process creation, equipped with a procedure to detect symmetric executions (ie., which differ only by the identities of processes). This allows to reduce…

计算机科学中的逻辑 · 计算机科学 2013-02-15 Łukasz Fronc
‹ 上一页 1 2 3 10 下一页 ›